The paper proposes Task-Aware Coactivation Grouping (TACG) to significantly reduce communication costs in multi-task MoE inference by grouping experts based on task-specific co-activation patterns, ou…

The paper proposes DAG-MoE, a novel sparse Mixture-of-Experts framework that replaces standard weighted-sum aggregation with structural aggregation to enhance model performance and enable multi-step r…

A co-designed hardware-software approach for task-conditional sparsity in multi-task inference models, reducing FLOPs, latency, and energy.

This paper proposes a semantic-aware task clustering method for Cooperative multi-task semantic communication (CMT-SemCom) to ensure constructive cooperation and mitigate destructive cooperation and n…

CORE-MTL proposes a representation-centric framework that uses causal orthogonal representations to disentangle task-relevant structure from nuisance variation in multi-task learning, achieving superi…

This paper develops a policy-learning framework to optimally assign prediction tasks to multiple agents, considering individual agent expertise and capacity constraints, achieving systematic performan…

The paper introduces RA-MoE, a novel fine-tuning framework that leverages the internal routing structure of Mixture-of-Experts (MoE) models to improve performance on multilingual downstream tasks by a…

Mind-Omni introduces a unified multi-task framework that models the interplay between brain, vision, and language signals using a discrete diffusion paradigm, achieving state-of-the-art performance ac…

MAESTRO is a structured pruning framework designed for MoE language models that models autoregressive expert activation trajectories as Ergodic Markov chains, yielding a globally aware importance heur…

The paper proposes a unified framework to evaluate how different types of memory transfer benefit multi-trajectory inference for tool-use LLM agents, finding that the optimal memory method depends cri…

The paper introduces Multi-Response Training (MRT) to combat the 'mode lottery' problem in language model fine-tuning, showing that retaining multiple valid responses significantly improves distributi…

CA-BED is a novel framework that improves LLM performance in interactive question-answering by integrating Bayesian Experimental Design to strategically select questions that maximize information gain…

The paper introduces OCC-RAG, a family of compact, task-specialized Small Language Models (SLMs) designed to achieve highly faithful, multi-hop question answering grounded strictly in provided context…

The paper challenges the conclusion that LLMs lack reasoning by demonstrating that reported performance drops on GSM-Symbolic are often statistically weak and partially attributable to dataset biases,…

CORTIS is a text-only adaptation framework that fine-tunes spoken language models for task-oriented voice agents using text-form task supervision.

The paper introduces PlanRAG, a framework for Retrieval-Augmented Generation (RAG) that models exploratory reasoning problems as logical query trees, addressing representation and optimization gaps be…

A unified multi-task malware analysis framework based on Mixture of Experts (MoE) architectures is proposed for malware family classification, packed versus unpacked detection, and malware versus beni…

The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved…

MOOSE-Copilot is a novel web-based framework that unifies scientific hypothesis discovery by formalizing human-AI interaction, significantly improving performance over autonomous LLM baselines.